Aircraft gliding section flight range online prediction method based on integrated neural network

Abstract

The invention discloses an integrated neural network-based aircraft gliding section flight range online prediction method, and belongs to the technical field of aircraft flight. The method comprises the following steps: before an aircraft takes off, selecting sample points on a predetermined standard trajectory and randomly and equally dividing into multiple groups; calculating a trajectory drop point longitude and a trajectory drop point latitude; the input of the sample library is a ballistic calculation initial value, and the output of the sample library is the maximum value and the minimum value of the ballistic drop point longitude and latitude; training each group of sample points to obtain a flight range prediction neural network; and inputting the current flight state of the aircraft, performing flight range prediction by adopting a flight range prediction neural network, performing integrated neural network prediction on a prediction result, and then obtaining a flight prediction result. According to the method, the prediction accuracy is improved, the strong nonlinear dynamic process of the gliding section of the aircraft is considered, the maximum flight range can be obtained according to the current state of the aircraft, the flight range is calculated in real time by adopting a neural network offline training and online use mode, and the method has good engineering practicability.

Description

technical field [0001] The invention relates to an online prediction method for the flight range of the gliding section of an aircraft based on an integrated neural network, and belongs to the technical field of aircraft flight. Background technique [0002] The dynamic process of aircraft glide stage has strong nonlinear characteristics. The traditional online prediction method of flight range based on approximate linear model has low calculation accuracy, and the calculation time of flight range prediction method based on nonlinear model is long, which cannot meet the requirements of online calculation. Therefore, it is urgent to develop a new online prediction method of flight range. Contents of the invention [0003] In order to solve the problems existing in the background technology, the present invention provides an online prediction method for the flight range of the gliding segment of an aircraft based on an integrated neural network. [0004] To achieve the abo...

AI Technical Summary

Problems solved by technology

The traditional online prediction method of flight range based on approximate linear model has low calculation accuracy, and the calculation time of flight range prediction method based on nonlinear model is long, which cannot meet the requirements of online calculation

Images